From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1LAsKu-0003hy-68 for qemu-devel@nongnu.org; Thu, 11 Dec 2008 15:40:40 -0500 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1LAsKs-0003hm-4N for qemu-devel@nongnu.org; Thu, 11 Dec 2008 15:40:39 -0500 Received: from [199.232.76.173] (port=46565 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1LAsKs-0003hj-01 for qemu-devel@nongnu.org; Thu, 11 Dec 2008 15:40:38 -0500 Received: from yw-out-1718.google.com ([74.125.46.158]:46572) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1LAsKr-0003i6-M4 for qemu-devel@nongnu.org; Thu, 11 Dec 2008 15:40:37 -0500 Received: by yw-out-1718.google.com with SMTP id 6so519814ywa.82 for ; Thu, 11 Dec 2008 12:40:36 -0800 (PST) Message-ID: <49417ABD.6020908@codemonkey.ws> Date: Thu, 11 Dec 2008 14:40:29 -0600 From: Anthony Liguori MIME-Version: 1.0 Subject: Re: [Qemu-devel] [RFC] Replace posix-aio with custom thread pool References: <493FFAB6.2000106@codemonkey.ws> <493FFC8E.9080802@redhat.com> <49400F69.8080707@codemonkey.ws> <20081210190810.GG18814@random.random> <20081211131222.GA14908@random.random> <494130B5.2080800@redhat.com> <20081211155335.GE14908@random.random> <49413B9C.3030703@redhat.com> <20081211164947.GD6809@random.random> <49414BC9.5090905@redhat.com> <20081211181116.GE6809@random.random> In-Reply-To: <20081211181116.GE6809@random.random> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Andrea Arcangeli Cc: Gerd Hoffmann , kvm-devel , qemu-devel@nongnu.org Andrea Arcangeli wrote: > On Thu, Dec 11, 2008 at 06:20:09PM +0100, Gerd Hoffmann wrote: > >> Andrea Arcangeli wrote: >> >>> On Thu, Dec 11, 2008 at 05:11:08PM +0100, Gerd Hoffmann wrote: >>> >>>> Yes. But kernel aio requires O_DIRECT, so aio users are affected >>>> nevertheless. >>>> >>> Are you sure? It surely wasn't the case... >>> >> Tons of docs say so, but might be they are wrong, I didn't check. >> > > I guess those tons of docs are just wrong then ;). I see no mention of > O_DIRECT in `man io_submit` at least... io_submit blocks unless you use O_DIRECT for most filesystems that people care about. This is why the current trends are toward kernel space thread pools. It would be very difficult to modify every file system to support true asynchronous buffered IO. Also, it's pretty clear that linux-aio doesn't have a strong future so I don't think it's very worthwhile to support. Regards, Anthony Liguori Regards, Anthony Liguori